def generate_model(self, variant_name, models_folder):
training_file = variant_name + ".t"
if self.feature_scaling:
self.scale_features(variant_name, models_folder)
training_file += ".scale"
(y, x) = svm_read_problem(training_file)
self.m_prob = svm.svm_problem(y, x, self.m_params.kernel_type == PRECOMPUTED)
libsvm_path = os.environ['LIBSVM_PATH']
scaled_filename = os.path.abspath(training_file)
cp = "python grid.py " + scaled_filename
curdir = os.getcwd()
os.chdir(libsvm_path + "/tools/")
result = call_process(cp)
os.chdir(curdir)
C,g,rate = [float(l) for l in result.split("\n")[-2].split(" ")]
print "C: %.8f, gamma: %.8f\n" % (C,g)
self.m_params.C = C
self.m_params.gamma = g
print "\n-----------------------------"
model = svm.svm_train(self.m_prob, self.m_params)
print "-----------------------------\n"
svm_save_model(models_folder + variant_name + ".model", model)
def generate_model(self, variant_name, models_folder):
training_file = variant_name + ".t"
if self.feature_scaling:
self.scale_features(variant_name, models_folder)
training_file += ".scale"
(y, x) = svm_read_problem(training_file)
self.m_prob = svm.svm_problem(y, x,
self.m_params.kernel_type == PRECOMPUTED)
libsvm_path = os.environ['LIBSVM_PATH']
scaled_filename = os.path.abspath(training_file)
cp = "python grid.py " + scaled_filename
curdir = os.getcwd()
os.chdir(libsvm_path + "/tools/")
result = call_process(cp)
os.chdir(curdir)
C, g, rate = [float(l) for l in result.split("\n")[-2].split(" ")]
print "C: %.8f, gamma: %.8f\n" % (C, g)
self.m_params.C = C
self.m_params.gamma = g
print "\n-----------------------------"
model = svm.svm_train(self.m_prob, self.m_params)
print "-----------------------------\n"
svm_save_model(models_folder + variant_name + ".model", model)
def compute_best_svm_radius(train_matrix, train_labels, val_matrix, val_labels,
radius_to_consider):
"""Compute the optimal SVM radius using the provided training and evaluation datasets.
You should only consider radius values within the radius_to_consider list.
You should use accuracy as a metric for comparing the different radius values.
Args:
train_matrix: The word counts for the training data
train_labels: The spma or not spam labels for the training data
val_matrix: The word counts for the validation data
val_labels: The spam or not spam labels for the validation data
radius_to_consider: The radius values to consider
Returns:
The best radius which maximizes SVM accuracy.
"""
# *** START CODE HERE ***
results = []
for r in radius_to_consider:
model = svm.svm_train(train_matrix, train_labels, r)
pred = svm.svm_predict(model, val_matrix, r)
accuracy = np.mean(pred == val_labels)
print("Radius: {}, Accuracy: {}".format(r, accuracy))
record = {"r": r, 'acc': accuracy}
results.append(record)
results.sort(key=lambda x: -x['acc'])
return results[0]['r']
def __init__(self,arg1,arg2=None): if arg2 == None: # create model from file filename = arg1 self.model = svmc.svm_load_model(filename) else: # create model from problem and parameter prob,param = arg1,arg2 self.prob = prob if param.gamma == 0: param.gamma = 1.0/prob.maxlen msg = svmc.svm_check_parameter(prob.prob,param.param) if msg: raise ValueError, msg self.model = svmc.svm_train(prob.prob,param.param) #setup some classwide variables self.nr_class = svmc.svm_get_nr_class(self.model) self.svm_type = svmc.svm_get_svm_type(self.model) #create labels(classes) intarr = svmc.new_int(self.nr_class) svmc.svm_get_labels(self.model,intarr) self.labels = _int_array_to_list(intarr, self.nr_class) svmc.delete_int(intarr) #check if valid probability model self.probability = svmc.svm_check_probability_model(self.model)
def train(xtrain, ytrain):
a = ada_train(xtrain, ytrain, 10)
g = gnb_train(xtrain, ytrain)
s = svm_train(xtrain, ytrain)
return a, g, s
nn_model.test_neural_network(test_X, test_Y)
<<<<<<< HEAD
rf.random_forest_train(train_X,train_Y)
rf.random_forest_test(test_X, test_Y)
=======
rf.random_forest_train(train_X,train_Y)
rf.random_forest_test(test_X, test_Y)
>>>>>>> d7c5221fc5e365f34a6b61e63a316a5b421943e5
dt.decisiontrain(train_X,train_Y)
dt.decisiontest(test_X, test_Y)
svm.svm_train(train_X,train_Y)
svm.svm_test(test_X,test_Y)
#random forest test for one sample of meal or no meal : not tested yet!
def model1_test_one_sample(test_sample):
#test_data = pcafeature.get_reduced_test_data(test_sample)
output = rf.rf_test_one_sample(test_sample)
#dt.dt_test_one(test_sample)
print(output)
return output